Skip to main content
Fig. 2 | BMC Bioinformatics

Fig. 2

From: Embedding covariate adjustments in tree-based automated machine learning for biomedical big data analyses

Fig. 2

Permutation importance from 100 runs of TPOT on the TG-GATEs data set. The gene names are displayed on the y-axis and the weighted (by testing score) averages of the mean score decrease as a percentage of the score are displayed on the x-axis. a resAdj TPOT; the top 20 features and 7 covariates are shown. The analyses were done at the probeset level, and for Rhoa there were two probesets among the top 20 features. b Classic TPOT; the top 20 features are shown. Also in this case, for some of the genes there were two probesets among the top 20 features

Back to article page